Model Card for resnet50_supcon_cifar100

This model is a small resnet50 trained on cifar100.

• Test Accuracy: 0.6854
• License: MIT

How to Get Started with the Model

Use the code below to get started with the model.

import detectors
import timm

model = timm.create_model("resnet50_supcon_cifar100", pretrained=True)

Training Data

Training data is cifar100.

Training Hyperparameters

• config: None

• model: resnet50_supcon_cifar100

• batch_size: 512

• epochs: 501

• lr: 0.5

• warmup_epochs: 10

• validation_frequency: 50

• output_features_dim: 128

• seed: 1

• debug: False

• dataset: cifar100

• training_mode: supcon

Testing Data

Testing data is cifar100.

---

This model card was created by Eduardo Dadalto.